Work Sampling

Work Sampling
Presented By,
Suhrita Ghosh (22)
Susmita Biswas (23)
Contents
 Definition
 Explaining Work Sampling
 Types of Work Sampling
 Procedure for Work Sampling
 Normal Distribution Curve
 Confidence Level
 Determining Sample Size
 Errors in Work Sampling
 Uses of Work Sampling
 Advantages of Work Sampling
 Disadvantages of Work Sampling
 Bibliography
Definition
 Work Sampling : A method of finding the percentage occurrence of
a certain activity by statistical sampling and random observations.
 Introduced by L.H.C. TIPPET of British cotton industry research
association in 1934.
 Also known as Activity Sampling or Random Sampling.
 Based upon laws of probability.
 A sample taken at random from a large group tends to

have the same pattern of distribution as the large group.
 Sample is the term used for the small representative

number.
 Population or Universe is the term used for the large group.
 Obtaining and analyzing only a part of the universe is

called Sampling.
 Larger the sample size, the more accurate or representative

it becomes with respect to the original “population”.
Explaining Work Sampling
 A panel of 480 blocks representing 480 minutes of a 8 hour day
arranged across the bottom of a board.
 The white blocks represent working time and the colored idle time.
 480 small pieces of paper are taken and numbered to represent
480 minutes in the 8 hour day.
 These slips kept in a hat and mixed thoroughly.
 A number is drawn and a mark placed on a bar at the time
corresponding to the number on the slip.
 40 such ‘random observations’ are done.

 Markings are on white represent observations of the worker
while working and those on colored represent him idle.
 Total of 6 idle observations were taken during the day.
 Therefore,
(6/40)*100=15
=15%
 This is the percentage of the day during which the worker
was idle as determined by work sampling.
State Tally Total
Working IIII IIII IIII IIII IIII IIII 34
Idle IIII I 6
Types of Work Sampling
 Activity or Delay Sampling- To measure the activities and delays of
workers or machines.
 Performance Sampling- To measure working time and nonworking

time of a person on a manual task, and to establish a performance
index or performance level for the person during his working time.
 Work Measurement- Under certain circumstances, to measure a

manual task, that is to establish a time standard for an operation.
Procedure
The following steps are required in making a work sampling

study:-
 Define the problem.
a. State the main objectives of the problem.

b. Describe in detail each element to be measurement.
 Obtain the approval of the department in which the work

sampling study is to be made. Obtain the co-operation of the
workers.
 Determine the desired accuracy of the final results.
 Make a preliminary estimate of the percentage occurrence of

the activity or delay to be measured, based on past experience
or a one-day or two-day preliminary work sampling study.
 Design the study.

a. Determine the number of observations to be made.
b. Determine the number of observers needed.
c. Determine the number of shifts needed.
d. Make detailed plans for taking the observations such
as the time and route to be followed by observer.
e. Design the observation form.
 Make the observation.
a. Make the observation and record the data.
b. Summarize the data at the end of each day.
c. Determine the control limits.
d. Plot the data on control charts at the end of each
day.
 Check the accuracy or precision of data at the end of the

day.
 Prepare the report and state conclusions.
 Make recommendations if called for.
Confidence Level
 It is necessary to decide what level of confidence is desired
in the final working sample.
 Most common confidence interval is 95% which means
that probability is 95% of the times

the random observations will
represent the facts and 5% of
the time, it will not.
Normal Distribution Curve
 It represents graphically the probability of the occurrence of
certain chance phenomenon.
 Normal distribution curve is described by 2 attributes :
x=average or measure of central dispersion
σ =standard deviation(deviation from average)
 From the previous figure,σp on both sides of x gives an area
of 68.27% of the total area.
 2σp on both sides of x gives an area of 95.45%.
 32σp on both sides of x gives an area of 99.73%.
 This is in fact the degree of confidence in our observations.

For e.g.
95% confidence level or 95% of the area under the
curve=1.96σp
99% confidence level or 99% of the area under the curve
=2.58σp
99.9% confidence level or 99.9% of the area under the curve
=3.3σp
Determination of sample size
 The proportion defective items ‘p’ in a large number of
items is to be drawn after observing the proportion defective
‘p1’ in a suitably selected sample size ‘n’ from the large
number of items.
 The standard deviation of ‘p1’ for sample size ‘n’, also

termed as Standard Error of Proportion,
given by,
σ p = √{p(1-p)}
√(n-1)
For large ‘n’ the expression can be approximated to:-
σ p = √{p(1-p)}
√n
 When ‘p’ is unknown, the average value of p1 computed from previous samples
maybe used in place of p.
 We have to decide the margin of error that we can allow for these observations.
 The formula for determining the number of observations is
given by :
P.S=Kσp
=K√p(1-p)
√n
p= percentage occurrence of the activity (working or non-

working) being measured in fraction.
s= error in fraction
K= a factor, the value of which depends on the desired
confidence level.
For e.g. 95% confidence level, K=1.96
n= number of observations required for the desired confidence
level and margin of error.
Error in work sampling
Work Sampling is subjected to two kinds of error.
 Observational Error: Occurs due to the presence and

behavior of the observer, the observed and/or environment
in which the observations are made.
Study is made on a finite period of time. The period may not

be representative.
Experimental Error:
 Due to finite number of random observations on a specified

activity, an experimental error is introduced which is a
measure of sampling variations in terms of Standard Error of
Proportion.
Uses of Work Sampling
 To aid in determination of time standards and delay allowances.
 To aid in the measurement of overall performances.
 To determine the nature and extent of cycles and ‘peak load’

variations in observable activity.
 To study the time utilization by supervisors and establishing

goals for supervision.
 To aid in job evaluation.
 To assist in engineering economy studies.
 To aid in manpower planning.
 For appraisal of safety performance.
 For appraisal of organizational efficiency.

Advantages of work sampling
 Comparatively simple method.
 Usually requires fewer man hours and costs less to make a

work sampling study than it does to make a continuous time
study.
 Observations may be taken over a period of days or weeks

thus decreasing the chance of day- to -day or week- to
-week variations affecting the results.
 Work sampling may be interrupted at any time without

affecting the result.
 Operator does not feel under too much pressure and

attention.
 A simultaneous work sampling study of several operation or
operators or machines maybe made by a single observer.
 Not necessary to use trained analyst for observers.
 Prolonged study is unnecessary since instantaneous observation

of the operator at random intervals during the working day.
 Less tedious and less fatiguing to make on the part of the

observer.
 A stop watch is not needed. If an electronic data collector is used,

the results are shown on a computer printout.
Disadvantages
 Not economical for studying a simple a single operator or

machine or for studying operators or machines located over
wide areas.
 No details about operation.

 No No details about operation
details about operation
Bibliography
 Introduction to work study( Indian Adaptation)

International Labor Office, Geneva
 Motion and time study design and measurement of

work(Seventh Edition)
-Ralph M. Barnes
THANK YOU

Work Sampling

Uploaded by

Copyright:

Available Formats

Work Sampling

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Work Sampling

Uploaded by

Copyright:

Available Formats

What are the different types of work sampling?

What are the different types of work sampling?

What are the steps involved in conducting a work sampling study?

What are the steps involved in conducting a work sampling study?

Work Sampling

 A sample taken at random from a large group tends to

 Sample is the term used for the small representative

 Population or Universe is the term used for the large group.

 Obtaining and analyzing only a part of the universe is

 Larger the sample size, the more accurate or representative

 Performance Sampling- To measure working time and nonworking

 Work Measurement- Under certain circumstances, to measure a

The following steps are required in making a work sampling

a. State the main objectives of the problem.

 Obtain the approval of the department in which the work

 Make a preliminary estimate of the percentage occurrence of

 Design the study.

 Check the accuracy or precision of data at the end of the

that probability is 95% of the times

 This is in fact the degree of confidence in our observations.

 The standard deviation of ‘p1’ for sample size ‘n’, also

p= percentage occurrence of the activity (working or non-

 Observational Error: Occurs due to the presence and

Study is made on a finite period of time. The period may not

 Due to finite number of random observations on a specified

 To aid in the measurement of overall performances.

 To determine the nature and extent of cycles and ‘peak load’

 To study the time utilization by supervisors and establishing

 To assist in engineering economy studies.

 To aid in manpower planning.

 For appraisal of safety performance.

 For appraisal of organizational efficiency.

 Usually requires fewer man hours and costs less to make a

 Observations may be taken over a period of days or weeks

 Work sampling may be interrupted at any time without

 Operator does not feel under too much pressure and

 Not necessary to use trained analyst for observers.

 Prolonged study is unnecessary since instantaneous observation

 Less tedious and less fatiguing to make on the part of the

 A stop watch is not needed. If an electronic data collector is used,

 Not economical for studying a simple a single operator or

 No details about operation.

 Introduction to work study( Indian Adaptation)

 Motion and time study design and measurement of

You might also like